Skip to main content
Glama

krusch_context_nudge

Idempotent

Audit proposed code diffs and actions against active project invariants, then tune rule weights from developer feedback to keep alignment checks accurate.

Instructions

Invariant auditor and alignment feedback loop. Checks proposed code diffs or actions against active project invariants, and adjusts rule weights based on developer feedback.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "krusch_context_nudge"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoCode or diff snippet to audit
hookNoAlias for trigger
actionNoAction: audit against invariants or submit feedbackaudit
projectNoTarget project
rule_idNoRule or memory ID when providing feedback
triggerNoTrigger point. Default: manual. ('every_turn' is disabled to prevent audit spam)manual
feedbackNoFeedback rating to tune rule weights
file_pathNoOptional target file path

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.2

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false; the description corroborates the non-read-only nature by disclosing that feedback mutates rule weights, so there is no contradiction. It adds real context about the two-mode behavior (audit versus weight tuning) that annotations do not convey, though it omits whether audits persist state or what feedback does to existing weights.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the tool's dual role and no filler. The opening phrase 'Invariant auditor and alignment feedback loop' is a bit of a jargon label, but the follow-up sentence immediately operationalizes it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with zero required parameters and no output schema, the description should clarify which parameters each mode needs (code/project for audit, rule_id/feedback for feedback) and roughly what an audit yields. It covers the conceptual role but leaves mode-specific invocation to be inferred from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and four parameters carry enums with their own descriptions, so the schema already explains code, action, trigger, and feedback values. The description adds only the framing that 'code' means a diff snippet and that feedback tunes weights, which is modest value beyond the schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource pair: auditing proposed code diffs or actions against active project invariants, plus a second feedback mode that tunes rule weights. It is distinguishable from memory-oriented siblings (remember/retrieve/revise), though it never names them or states the divide explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied — 'Checks proposed code diffs or actions' hints at pre-commit/pre-edit auditing, and 'adjusts rule weights based on developer feedback' hints at the feedback path. There is no explicit when-to-use versus when-not, no statement of prerequisites, and no guidance on choosing this over the sibling context tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.